{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Import Libraries\n",
    "import openai\n",
    "import langchain\n",
    "#import pinecone\n",
    "from langchain.document_loaders import PyPDFDirectoryLoader\n",
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "\n",
    "from langchain.llms import OpenAI\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from dotenv import load_dotenv\n",
    "load_dotenv()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Lets read the document\n",
    "def read_doc(directory):\n",
    "    file_loader=PyPDFDirectoryLoader(directory)\n",
    "    documents=file_loader.load()\n",
    "    return documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "61"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "doc=read_doc('documents/')\n",
    "len(doc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Divide the docs into chuncks\n",
    "def chunk_data(docs,chunk_size=800,chunk_overlap=50):\n",
    "    text_splitter=RecursiveCharacterTextSplitter(chunk_size=chunk_size,chunk_overlap=chunk_overlap)\n",
    "    docs=text_splitter.split_documents(docs)\n",
    "    return docs\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "187"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "documents=chunk_data(docs=doc)\n",
    "len(documents)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Embedding Technique of OPENAI\n",
    "embeddings=OpenAIEmbeddings(api_key=os.environ['OPENAI_API_KEY'])\n",
    "embeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1536"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectors=embeddings.embed_query(\"How are you?\")\n",
    "len(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pinecone import Pinecone, ServerlessSpec\n",
    "os.environ['PINECONE_API_KEY'] = \"870db653-5972-4c49-a639-6f497a3660dc\"\n",
    "pc = Pinecone(api_key=os.environ['PINECONE_API_KEY'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "\n",
    "index_name = \"langchainvector\"  # change if desired\n",
    "\n",
    "existing_indexes = [index_info[\"name\"] for index_info in pc.list_indexes()]\n",
    "\n",
    "if index_name not in existing_indexes:\n",
    "    pc.create_index(\n",
    "        name=index_name,\n",
    "        dimension=1536,\n",
    "        metric=\"cosine\",\n",
    "        spec=ServerlessSpec(cloud=\"aws\", region=\"us-east-1\"),\n",
    "    )\n",
    "    while not pc.describe_index(index_name).status[\"ready\"]:\n",
    "        time.sleep(1)\n",
    "\n",
    "index = pc.Index(index_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_pinecone import PineconeVectorStore\n",
    "\n",
    "docsearch = PineconeVectorStore.from_documents(documents, embeddings, index_name=index_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Similarity Retrieve Result\n",
    "def retrieve_query(query,k=2):\n",
    "    matching_results=docsearch.similarity_search(query,k=k)\n",
    "    return matching_results\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Matt Brown\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\langchain_core\\_api\\deprecation.py:139: LangChainDeprecationWarning: The class `OpenAI` was deprecated in LangChain 0.0.10 and will be removed in 0.3.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run `pip install -U langchain-openai` and import as `from langchain_openai import OpenAI`.\n",
      "  warn_deprecated(\n"
     ]
    }
   ],
   "source": [
    "from langchain.chains.question_answering import load_qa_chain\n",
    "from langchain import OpenAI\n",
    "llm=OpenAI(model_name=\"gpt-3.5-turbo-instruct\",temperature=0.5)\n",
    "chain=load_qa_chain(llm,chain_type=\"stuff\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [],
   "source": [
    "def retrieve_answers(query):\n",
    "    doc_search=retrieve_query(query)\n",
    "    print(doc_search)\n",
    "    response=chain.run(input_documents=doc_search,question=query)  \n",
    "    return response  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"What are indirect emissions?\"\n",
    "answer=retrieve_answers(query)\n",
    "print(answer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"What are scope 2 emissions?\"\n",
    "docs = docsearch.similarity_search(query,k=2)\n",
    "print(docs[0].page_content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "retriever = docsearch.as_retriever(search_type=\"mmr\")\n",
    "matched_docs = retriever.invoke(query)\n",
    "for i, d in enumerate(matched_docs):\n",
    "    print(f\"\\n## Document {i}\\n\")\n",
    "    print(d.page_content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "found_docs = docsearch.max_marginal_relevance_search(query, k=2, fetch_k=10)\n",
    "for i, doc in enumerate(found_docs):\n",
    "    print(f\"{i + 1}.\", doc.page_content, \"\\n\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}